{
  "id": "2006.15437",
  "version": "v1",
  "published": "2020-06-27T20:12:33.000Z",
  "updated": "2020-06-27T20:12:33.000Z",
  "title": "GPT-GNN: Generative Pre-Training of Graph Neural Networks",
  "authors": [
    "Ziniu Hu",
    "Yuxiao Dong",
    "Kuansan Wang",
    "Kai-Wei Chang",
    "Yizhou Sun"
  ],
  "comment": "Published on KDD 2020",
  "categories": [
    "cs.LG",
    "cs.SI",
    "stat.ML"
  ],
  "abstract": "Graph neural networks (GNNs) have been demonstrated to be powerful in modeling graph-structured data. However, training GNNs usually requires abundant task-specific labeled data, which is often arduously expensive to obtain. One effective way to reduce the labeling effort is to pre-train an expressive GNN model on unlabeled data with self-supervision and then transfer the learned model to downstream tasks with only a few labels. In this paper, we present the GPT-GNN framework to initialize GNNs by generative pre-training. GPT-GNN introduces a self-supervised attributed graph generation task to pre-train a GNN so that it can capture the structural and semantic properties of the graph. We factorize the likelihood of the graph generation into two components: 1) Attribute Generation and 2) Edge Generation. By modeling both components, GPT-GNN captures the inherent dependency between node attributes and graph structure during the generative process. Comprehensive experiments on the billion-scale Open Academic Graph and Amazon recommendation data demonstrate that GPT-GNN significantly outperforms state-of-the-art GNN models without pre-training by up to 9.1% across various downstream tasks.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-06-27T20:12:33.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "graph neural networks",
      "outperforms state-of-the-art gnn models",
      "significantly outperforms state-of-the-art gnn",
      "attributed graph generation task",
      "generative pre-training"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}